Newshot

ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering

Summary

arXiv:2603.13950v2 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-$k$ subset for reasoning. Prior work on attacking these systems competes for tool selection, assuming benign tools remain in the retrieved set; the robustness of the retrieval stage that produces this set is underexplored. This paper introduces ToolFlood, a retrieval-layer attack on tool-augmented LLM agents. Rather than altering which tool is chosen after retrieval, ToolFlood attacks retrieval itself: it injects a few attacker-controlled tools whose metadata is positioned to exploit the geometry of embedding space, so that these tools semantically span many user queries, dominate the top-k results, and push all benign tools out of the agent's context. ToolFlood uses a two-phase adversarial tool generation strategy. It first samples subsets of target queries and uses an LLM to iteratively gene…

Original text(via arXiv cs.CL)

Computer Science > Computation and Language

Title:ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering

Abstract:Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-$k$ subset for reasoning. Prior work on attacking these systems competes for tool selection, assuming benign tools remain in the retrieved set; the robustness of the retrieval stage that produces this set is underexplored. This paper introduces ToolFlood, a retrieval-layer attack on tool-augmented LLM agents. Rather than altering which tool is chosen after retrieval, ToolFlood attacks retrieval itself: it injects a few attacker-controlled tools whose metadata is positioned to exploit the geometry of embedding space, so that these tools semantically span many user queries, dominate the top-k results, and push all benign tools out of the agent's context. ToolFlood uses a two-phase adversarial tool generation strategy. It first samples subsets of target queries and uses an LLM to iteratively generate diverse tool names and descriptions. It then runs an iterative greedy selection that chooses tools maximizing coverage of remaining queries in embedding space under a cosine-distance threshold, stopping when all queries are covered or a budget is reached. We provide theoretical intuition of retrieval saturation and show on a large catalog (ToolBench) that ToolFlood achieves up to a 95\% attack success rate with a ~1\% injection rate. The code is available at: this https URL
Comments:Accepted to EACL 2027 (main)
Subjects:Computation and Language (cs.CL)
Cite as:arXiv:2603.13950 [cs.CL]
(or arXiv:2603.13950v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2603.13950 arXiv-issued DOI via DataCite

Submission history

Access Paper:

  • HTML (experimental)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.CL
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗